Systems and methods for predicting communication account identities across decentralized applications

Abstract

Methods and systems that use of a multi-tiered machine learning architecture that aggregates traits of blockchain and off-chain operations. The multi-tiered machine learning architecture then uses this data to generate recommendations related to account identities for communications (e.g., blockchain operations) that occur across decentralized applications.

What is claimed is: 
     
       1. A system for predicting communication account identities across decentralized applications based on aggregating traits of blockchain and off-chain operations using a multi-tiered machine learning architecture, the system comprising:
 cloud-based storage circuitry configured to:
 store a first tier of a machine learning architecture, wherein the first tier comprises:
 a first machine learning model trained to predict communication account identity traits of a first type based on historic communication data of the first type; 
 a second machine learning model trained to predict communication account identity traits of a second type based on historic communication data of the second type; and 
 an oracle layer for the first machine learning model and the second machine learning model; 
 
 store a second tier of the machine learning architecture, wherein the second tier comprises a plurality of rule sets for predicting communication account identities; 
 
 cloud-based control circuitry configured to:
 receive a first data feed, wherein the first data feed corresponds to a first type of communication data, wherein the first type of communication data is on-chain data, and wherein the first type of communication data indicates a blockchain network volume of pending communications; 
 receive a second data feed, wherein the second data feed corresponds to a second type of communication data, and wherein the second type of communication data indicates communication formats of pending communications; 
 generate a first feature input based on the first data feed; 
 generate a second feature input based on the second data feed; 
 input the first feature input into the first machine learning model to generate a first output, wherein the first output indicates a first communication account identity trait; 
 input the second feature input into the second machine learning model to generate a second output, wherein the second output indicates a second communication account identity trait; 
 generate, using the oracle layer for the first machine learning model and the second machine learning model, a third feature input based on the first output and the second output; 
 determine, based on the third feature input, a first rule set from a plurality of rule sets for predicting communication account identities; 
 receive a first communication; 
 predict a first communication account identity for the first communication based on the first rule set; 
 determine an identity probability at a first time based on the first communication account identity; 
 determine an off-chain operation required for the first communication based on the identity probability; and 
 determine a recommendation based on the off-chain operation required for the first communication; and 
 
 cloud-based input/output circuitry configured to generate for display, on a user interface, the recommendation based on the first communication account identity. 
 
     
     
       2. A method for predicting communication account identities across decentralized applications based on aggregating traits of blockchain and off-chain operations using a multi-tiered machine learning architecture, the method comprising:
 receiving a first data feed, wherein the first data feed corresponds to a first type of communication data, wherein the first type of communication data is blockchain data; 
 receiving a second data feed, wherein the second data feed corresponds to a second type of communication data, wherein the second type of communication data is off-chain data; 
 receiving a first communication; 
 generating a first feature input based on the first data feed; 
 generating a second feature input based on the second data feed; 
 inputting the first feature input into a first machine learning model to generate a first output, wherein the first machine learning model is trained to predict first communication account identity traits based on historic communication data of the first type, and wherein the first output indicates a first communication account identity trait; 
 inputting the second feature input into a second machine learning model to generate a second output, wherein the second machine learning model is trained to predict second communication account identity traits based on historic communication data of the second type, and wherein the second output indicates a second communication account identity trait; 
 generating, using an oracle layer for the first machine learning model and the second machine learning model, a third feature input based on the first output and the second output; 
 determining, based on the third feature input, a first rule set from a plurality of rule sets for predicting communication account identities; 
 predicting a first communication account identity for the first communication based on the first rule set; and 
 generating for display, on a user interface, a recommendation based on the first communication account identity. 
 
     
     
       3. The method of  claim 2 , wherein receiving the first data feed and the second data feed further comprises:
 receiving a multi-modal data feed, wherein the multi-modal data feed corresponds to a plurality of types of communication data; and 
 segregating the multi-modal data feed into the first data feed and the second data feed. 
 
     
     
       4. The method of  claim 3 , wherein the multi-modal data feed comprises real-time data received from a plurality of sources. 
     
     
       5. The method of  claim 2 , further comprising:
 receiving a second communication; and 
 predicting a second communication account identity for the second communication based on the first rule set, wherein the recommendation is further based on the second communication account identity. 
 
     
     
       6. The method of  claim 2 , further comprising:
 determining an identity probability at a first time based on the first communication account identity; 
 comparing the identity probability at the first time to a threshold identity probability; and 
 determining the recommendation based on comparing the identity probability at the first time to the threshold identity probability. 
 
     
     
       7. The method of  claim 2 , further comprising:
 determining an identity probability at a first time based on the first communication account identity; 
 determining an off-chain operation required for the first communication based on the identity probability; and 
 determining the recommendation based on the off-chain operation required for the first communication. 
 
     
     
       8. The method of  claim 2 , wherein the first output indicates the first communication account identity trait as a series of probabilities corresponding to respective values for the first data feed. 
     
     
       9. The method of  claim 2 , further comprising processing the first feature input through the first machine learning model in parallel with processing the second feature input through the second machine learning model. 
     
     
       10. The method of  claim 2 , wherein predicting the first communication account identity for the first communication based on the first rule set further comprises:
 determining a first trait of the first communication; and 
 applying the first rule set to the first trait. 
 
     
     
       11. The method of  claim 10 , wherein the first trait corresponds to whether the first communication is dependent on a second communication. 
     
     
       12. A non-transitory computer-readable medium comprising instructions that when executed by one or more processors cause operations comprising:
 receiving a first data feed, wherein the first data feed corresponds to a first type of communication data, wherein the first type of communication data is blockchain data; 
 receiving a second data feed, wherein the second data feed corresponds to a second type of communication data, wherein the second type of communication data is off-chain data; 
 receiving a first communication; 
 generating a first feature input based on the first data feed; 
 generating a second feature input based on the second data feed; 
 inputting the first feature input into a first machine learning model to generate a first output, wherein the first machine learning model is trained to predict first communication account identity traits based on historic communication data of the first type, and wherein the first output indicates a first communication account identity trait; 
 inputting the second feature input into a second machine learning model to generate a second output, wherein the second machine learning model is trained to predict second communication account identity traits based on historic communication data of the second type, and wherein the second output indicates a second communication account identity trait; 
 generating, using an oracle layer for the first machine learning model and the second machine learning model, a third feature input based on the first output and the second output; 
 determining, based on the third feature input, a first rule set from a plurality of rule sets for predicting communication account identities; 
 predicting a first communication account identity for the first communication based on the first rule set; and 
 generating for display, on a user interface, a recommendation based on the first communication account identity. 
 
     
     
       13. The non-transitory computer-readable medium of  claim 12 , wherein receiving the first data feed and the second data feed further comprises:
 receiving a multi-modal data feed, wherein the multi-modal data feed corresponds to a plurality of types of communication data; and 
 segregating the multi-modal data feed into the first data feed and the second data feed. 
 
     
     
       14. The non-transitory computer-readable medium of  claim 13 , wherein the multi-modal data feed comprises real-time data received from a plurality of sources. 
     
     
       15. The non-transitory computer-readable medium of  claim 12 , wherein the instructions further cause operations comprising:
 receiving a second communication; and 
 predicting a second communication account identity for the second communication based on the first rule set, wherein the recommendation is further based on the second communication account identity. 
 
     
     
       16. The non-transitory computer-readable medium of  claim 12 , wherein the instructions further cause operations comprising:
 determining an identity probability at a first time based on the first communication account identity; 
 comparing the identity probability at the first time to a threshold identity probability; and 
 determining the recommendation based on comparing the identity probability at the first time to the threshold identity probability. 
 
     
     
       17. The non-transitory computer-readable medium of  claim 12 , wherein the instructions further cause operations comprising:
 determining an identity probability at a first time based on the first communication account identity; 
 determining an off-chain operation required for the first communication based on the identity probability; and 
 determining the recommendation based on the off-chain operation required for the first communication. 
 
     
     
       18. The non-transitory computer-readable medium of  claim 12 , wherein the first output indicates the first communication account identity trait as a series of probabilities corresponding to respective values for the first data feed. 
     
     
       19. The non-transitory computer-readable medium of  claim 12 , wherein the instructions further cause operations comprising processing the first feature input through the first machine learning model in parallel with processing the second feature input through the second machine learning model. 
     
     
       20. The non-transitory computer-readable medium of  claim 12 , wherein predicting the first communication account identity for the first communication based on the first rule set further comprises:
 determining a first trait of the first communication, wherein the first trait corresponds to whether the first communication is dependent on a second communication, and 
 applying the first rule set to the first trait.